LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models

TL;DR

LMTuner is a user-friendly, modular training framework that simplifies fine-tuning large language models, supporting various methods and scales from small to extremely large models with minimal setup.

Contribution

The paper introduces LMTuner, a highly usable, integrable, and scalable system that reduces training complexity and supports diverse fine-tuning techniques for large language models.

Findings

Enables training of models from 300M to 130B parameters on a single server.

Allows novice users to start training within five minutes.

Supports multiple efficient fine-tuning methods like LoRA and QLoRA.

Abstract

With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to increase. Currently, the predominantly employed frameworks lack modular design, it often takes a lot of coding work to kickstart the training of LLM. To address this, we present "LMTuner", a highly usable, integrable, and scalable system for training LLMs expeditiously and with minimal user-input. LMTuner comprises three main modules - the Interaction, Training, and Inference Modules. We advocate that LMTuner's usability and integrality alleviate the complexities in training large language models. Remarkably, even a novice user could commence training large language models within five minutes. Furthermore, it integrates DeepSpeed frameworks and supports Efficient Fine-Tuning methodologies like Low Rank Adaptation (LoRA), Quantized LoRA (QLoRA), etc., enabling the training of language models scaling from 300M to a whopping 130B parameters using a single server. The LMTuner's homepage (https://wengsyx.github.io/LMTuner/)and screencast video (https://youtu.be/nsXmWOmN3rE) are now publicly available.